Intrinsic decomposition for stereoscopic images

Xie, Dehua; Liu, Shuaicheng; Lin, Kaimo; Zhu, Shuyuan; Zeng, Bing

doi:10.1109/icip.2016.7532657

Cited by 5 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent progress in deep learning encourages researchers in the field to use convolutional neural network (CNN) based approaches to solve the inversion problem like Son & Lee (2016) or Shi et al (2017). Few works consider a non-local strategy like Xie et al (2016). They encourage distant clusters that have the same color to have the same reflectance.…”

Section: Introductionmentioning

confidence: 99%

Intrinsic RGB and multispectral images recovery by independent quadratic programming

Krebs¹,

Benezeth²,

Marzani³

2020

PeerJ Computer Science

View full text Add to dashboard Cite

This work introduces a method to estimate reflectance, shading, and specularity from a single image. Reflectance, shading, and specularity are intrinsic images derived from the dichromatic model. Estimation of these intrinsic images has many applications in computer vision such as shape recovery, specularity removal, segmentation, or classification. The proposed method allows for recovering the dichromatic model parameters thanks to two independent quadratic programming steps. Compared to the state of the art in this domain, our approach has the advantage to address a complex inverse problem into two parallelizable optimization steps that are easy to solve and do not require learning. The proposed method is an extension of a previous algorithm that is rewritten to be numerically more stable, has better quantitative and qualitative results, and applies to multispectral images. The proposed method is assessed qualitatively and quantitatively on standard RGB and multispectral datasets.

show abstract

Section: Introductionmentioning

confidence: 99%

Intrinsic RGB and multispectral images recovery by independent quadratic programming

Krebs¹,

Benezeth²,

Marzani³

2020

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…In recent years, lots of topics related to stereoscopic images and videos have been explored, such as stereoscopic movie making [32], stereoscopic warping [33]- [35], cloning [36], inpainting [37], stitching [38], [39], retargeting [40], editing [41]- [43], stabilization [44], [45], relighting [46], and so on. However, few work has targeted the problem of stereoscopic intrinsic image decomposition [47].…”

Section: Introductionmentioning

confidence: 99%

View-Consistent Intrinsic Decomposition for Stereoscopic Images

et al. 2019

Self Cite

View full text Add to dashboard Cite

In this paper, we focus on the intrinsic image decomposition problem for stereoscopic image pairs. The existing methods cannot be applied directly to decompose stereoscopic images, as it often produces inconsistent reflectance (albedo) and 3D artifacts after the decomposition. We propose a straightforward yet effective framework that enables a high-quality decomposition for stereoscopic pairs. First, retinex-based constraints are employed to coarsely classify the observed image gradients into two categories that are caused by reflectance changes and illumination variations, respectively. Second, reflectance-consistent constraints are added to control the reflectance consistency between the left and right views. Since this problem is highly ill-posed, we further analyze local and non-local image textures regularized by super-pixels within and across two views to reduce reflectance ambiguity. Lastly, absolute-scale constraints are employed to normalize the decomposition results. Extensive experiments on the real-world stereoscopic images and synthetic stereoscopic images reveal that our method can readily achieve high-quality decomposition performance.

show abstract

“…Recent progress in deep learning encourages researchers in the field to use CNN (convolutional neural network) based approaches to solve the inversion problem like Son and Lee (2016) or Shi et al (2017). Few works consider non-local strategy like Xie et al (2016). They encourage distant clusters that have the same color to have the same reflectance.…”

mentioning

confidence: 99%

Peer Review #1 of "Intrinsic RGB and multispectral images recovery by independent quadratic programming (v0.1)"

2020

View full text Add to dashboard Cite

This work introduces a method to estimate reflectance, shading, and specularity from a single image. Reflectance, shading, and specularity are intrinsic images derived from the dichromatic model. Estimation of these intrinsic images has many applications in computer vision such as shape recovery, specularity removal, segmentation or classification. The proposed method allows for recovering the dichromatic model parameters thanks to two independent quadratic programming steps. Compared to the state of the art in this domain, our approach has the advantage to address a complex inverse problem into two parallelizable optimization steps that are easy to solve and do not require learning. The proposed method is an extension of a previous algorithm that is rewritten to be numerically more stable, has better quantitative and qualitative results, and applies to multispectral images. The proposed method is assessed qualitatively and quantitatively on standard RGB and multispectral datasets.

show abstract

Intrinsic decomposition for stereoscopic images

Cited by 5 publications

References 29 publications

Intrinsic RGB and multispectral images recovery by independent quadratic programming

Intrinsic RGB and multispectral images recovery by independent quadratic programming

View-Consistent Intrinsic Decomposition for Stereoscopic Images

Peer Review #1 of "Intrinsic RGB and multispectral images recovery by independent quadratic programming (v0.1)"

Contact Info

Product

Resources

About